AI·Apple filed a federal lawsuit on July 10, 2026, accusing OpenAI of trade-secret theft by poaching Apple engineers and exploiting a post-departure access bug; the suit targets OpenAI's hardware ambitions and a possible AI-powered iPhone rival.
Search
What are you looking for?
19 results for “hardware”
AI·Sources say China's DeepSeek is developing its own AI chip, potentially advancing domestic AI hardware capabilities amid global tensions.
AI·Momenta listed on HKEX and soared over 6% on day one, securing global capital, while Mushroom Car Network's ToG Robobus model lags due to heavy hardware investment and cashflow pressure despite earlier physical AI claims.
AI·A user shares benchmarks of dual RTX 3090 and Titan RTX cards running llama.cpp with Qwen3.6-27B at 180k context, comparing tensor and pipeline parallel modes for PCIe transfer efficiency.
AI·The author benches a quad 5060Ti setup for Qwen3.6-27B code generation using MTP, reporting 608 tokens/s prefill and 52.2 tokens/s decode at 256k context on a cost-effective build.
AI·The post shares practical recipes and benchmarks for running LLMs on popular consumer hardware, with a new website listing hardware-filtered setups and user-voted usage stats.
AI·Introduces Flaxeo Image, a local desktop UI for Stable Diffusion C++ that exposes model, hardware, and video options.
AI·User with RTX 4090, 3090Ti, and 128GB RAM struggles to run larger models like 122B due to VRAM limits while Qwen3.6-27B runs efficiently without using system RAM.
AI·A $100 setup using three NVIDIA P102 cards delivers 20 GB VRAM and 448 GB/s memory bandwidth, sufficient for three concurrent LLM users with high context and better speeds than costlier lower-VRAM cards.
AI·Identifies dual 3060 MoE loading limit at 12 layers VRAM for Qwen3 35B/122B with CPU offload.
AI·User compares 5090 at 600W full compute and prompt processing vs shunt-modded 6000 PRO MaxQ water-cooled at 300-600W.
AI·Discusses feasibility of running Qwen 122B on 64GB RAM + 24GB VRAM and suitable settings.
AI·User upgrading from dual RTX 3090 asks for advice on adding cards for 100-110 GB model support, weighing 2x modded 48 GB 4090, 2x A6000, or 2x 5090 in hybrid setup.
AI·Questions costs and viability of aftermarket SXM2 boards for two V100 GPUs, comparing to consumer GPU setups.
AI·Reports EPYC 9374F CCD benchmarks using ik_llama.cpp; finds limited decoding gains vs older 9135 at low thread counts.
AI·The book "RISC-V Microprocessor System-on-Chip Design" provides a comprehensive guide to designing RISC-V-based SoCs.
Semantic audio applications increasingly require controllable generation on commodity and embedded hardware rather than through framework-heavy datacenter stacks. We present aria, a dependency-free native runtime that runs the complete text-to-music pipeline of Stable Audio~3 (SA3) on ordinary GPUs, CPU-only machines, and a Raspberry~Pi~5, with no Python or deep-learning framework underneath. Our main contribution is a study of quantization: running the model at lower numerical precision to fit…
OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.
Share what your favorite models are right now and why. Given the nature of the beast in evaluating VLMs (untrustworthiness of benchmarks, immature tooling, intrinsic stochasticity), please be as detailed as possible in describing your setup (at least hardware and inference engine) nature of your usage (what applications, how much, personal/professional use) tools/frameworks/prompts etc. Rules Onl…